Philip Pham
I am currently a software engineer at Waymo, where I apply machine learning to motion planning.
Before, I worked in Google Research. My research focused on increasing model capacity and understanding inductive biases of neural networks. Natural language processing (NLP) was the main application area.
Previously at Google, I worked on internal web applications. I studied mathematics at Duke University (B.S.) and University of Pennsylvania (M.A.) and statistics at the University of Washington.
Authored Publications
Sort By
Google
ReadTwice: Reading Very Large Documents with Memories
Yury Zemlyanskiy
Joshua Ainslie
Michiel de Jong
Ilya Eckstein
Proceedings of NAACL (2021) (to appear)
Long Range Arena : A Benchmark for Efficient Transformers
Yi Tay
Samira Abnar
Yikang Shen
Jinfeng Rao
Sebastian Ruder
ICLR 2021 (to appear)
OmniNet: Omnidirectional Representations from Transformers
Yi Tay
Vamsi Aribandi
ICML 2021
Fair Hierarchical Clustering
Benjamin Moseley
Marina Knittel
Yuyan Wang
Neurips 2020
Neural Structured Learning in TensorFlow: Hands-On Tutorial at KDD
Chun-Sung Ferng
George Yu
(2020), pp. 3501-3502
Big Bird: Transformers for Longer Sequences
Manzil Zaheer
Guru Prashanth Guruganesh
Joshua Ainslie
Anirudh Ravula
Qifan Wang
Li Yang
NeurIPS (2020)
ETC: Encoding Long and Structured Inputs in Transformers
Anirudh Ravula
Joshua Ainslie
Li Yang
Qifan Wang
Vaclav Cvicek
2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)
